Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 35340
    Prev
    Next
    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash

    references to sports events and player performances.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags bits of document‐level metadata and formatting markup—things like header IDs, start/end markers, and date stamps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    俺は
    -0.07
     Julio
    -0.07
     corres
    -0.06
    左右
    -0.06
     ∨
    -0.06
     Iterator
    -0.06
     dá
    -0.06
     دختر
    -0.06
     dictates
    -0.06
     Osmanlı
    -0.06
    POSITIVE LOGITS
    .setImage
    0.07
    ormsg
    0.07
    pcs
    0.07
    erot
    0.07
     componentName
    0.06
     Leo
    0.06
    .stop
    0.06
    oxetine
    0.06
    .userid
    0.06
    _SLOT
    0.06
    Activations Density 0.022%

    No Known Activations